Identification of clinically relevant protein targets in prostate cancer with 2D-DIGE coupled mass spectrometry and systems biology network platform

Abstract

Prostate cancer (PCa) is the most common type of cancer found in men and among the leading causes of cancer death in the western world. In the present study, we compared the individual protein expression patterns from histologically characterized PCa and the surrounding benign tissue obtained by manual micro dissection using highly sensitive two-dimensional differential gel electrophoresis (2D-DIGE) coupled with mass spectrometry. Proteomic data revealed 118 protein spots to be differentially expressed in cancer (n = 24) compared to benign (n = 21) prostate tissue. These spots were analysed by MALDI-TOF-MS/MS and 79 different proteins were identified. Using principal component analysis we could clearly separate tumor and normal tissue and two distinct tumor groups based on the protein expression pattern. By using a systems biology approach, we could map many of these proteins both into major pathways involved in PCa progression as well as into a group of potential diagnostic and/or prognostic markers. Due to complexity of the highly interconnected shortest pathway network, the functional sub networks revealed some of the potential candidate biomarker proteins for further validation. By using a systems biology approach, our study revealed novel proteins and molecular networks with altered expression in PCa. Further functional validation of individual proteins is ongoing and might provide new insights in PCa progression potentially leading to the design of novel diagnostic and therapeutic strategies.

Figure 1. Representative 2-DE proteome map of prostate tissue from tumor vs. benign samples.

Proteins were resolved by IEF over the pI range 4–7, followed by 12.5% SDS-PAGE and overlaid by Delta2D. After extraction from tissues, proteins were labeled with Cy3 and Cy5. An internal standard comprised of equal amount of proteins from all samples (benign and PCa groups) was labeled with Cy2 and included in all gels. The green spots indicate downregulated proteins, while the red spots indicate upregulated proteins in PCa relative to the corresponding benign tissue. The identified proteins that showed significantly altered expression in the PCa are indicated with arrows and labeled with the respectives protein IDs.

Figure 2. Cluster analysis and Gene Ontology of differential expressed proteins.

(A) Unsupervised clustering (euclidean distance measure and the ‘average’ agglomeration method) was performed using the log transformed expression protein values of 45 samples. The samples are shown horizontally, the proteins vertically. The dendrograms represent the distances between the clusters. In the upper color bar, the tumor samples are marked in red, the normal tissues are shown in green. (B) Biological processes regulated by the all significant differentially expressed proteins assessed by Gene Ontology search and summarized according to their functions.

Figure 3. Principal component analysis can separate normal and tumor tissue.

(A) Scatterplot of the first three principal components of PCA from the protein expression data. The blue stars represent the normal tissues, whereas the red stars show tumors. (B) Distribution of information with respect to differential expression between tumor and normal tissues. Each cross represents a protein. The p-values in two-sided t-test are represented by the x-axis, whereas the projections (red: projection onto S3, blue: projection onto complementary space) are represented by the values on the y-axis. Apparently for all proteins with significant differential expression in the original data (log10(p)<−2) the differential expression of the residual component (blue stars) is not significant (log10(p)<−1), whereas the p-values of the PCA-based components (red stars) are similar to the original p-values (x-axis). (C–D) Median accuracy and odds ratio of predictive tumor/normal classification. The blue curves show the increase of model quality by increased sample size used for biomarker model. The red stars show the qualities of the logit model based on the first three principal components. (E) The output of the regression model (y-axis) indicates the existence of two tumor classes differing significantly according to their separability. Normal tissues (blue and green boxes) using protein expression.

Figure 4. Functional classification of differential expressed proteins in different tumor groups.

(A) The biological processes, (B) molecular functions and (C) cellular compartments regulated by the differentially expressed proteins between both tumor groups assessed by Gene Ontology search.

Figure 5. Protein network of differentially expressed proteins in PCa.

(A) GeneGO MetaCore™ was used to generate a network of direct connections between all identified proteins with altered expression. Red, green, and gray arrows indicate negative, positive, and unspecified effects, respectively. Many of the identified proteins mapped to AR, p53 and c-Myc pathways involved in PCa progression where as some proteins were not connected in network. (B) To validate major hubs of the network c-Myc expression at transcriptional level assed by real time PCR from an independent set of samples. Results showed significant increase in the amount of c-Myc mRNA suggests it may have direct/indirect regulation of its connected proteins of shortest network. (C) Enrichment of GeneGo diseases by topologically significant proteins identified using all differentially expressed proteins. Data represents differentially expressed proteins mapped to prostatic neoplasms with highest significance followed by male genital neoplasms.

Figure 6. Protein subnetworks of differentially expressed proteins in PCa.

(A–D) Protein-protein physical/functional interaction sub networks generated by Ingenuity Pathway Analysis tool. Grey filled boxes are the differentially expressed proteins. Only significant sub networks were shown in the figure.

Figure 7. Western blot analysis of DDAH1, ARG2, eIF4A3, Prdx3, Prdx4 and PAWR in benign and PCa tissues.

Protein expression identified by western blotting and only representative blots were shown here. The protein expression levels of the analysed target proteins have shown their over expression in PCa compared to normal tissue. GAPDH was used as an internal loading control.

Figure 8. Expression of several protein candidates is regulated at transcriptional level.

Quantitative reverse transcription-PCR of transcripts (A) FKBP4, (B) Prdx4 and (C) PPA2 shown from benign prostate tissue (black bars) and localized prostate cancer (grey bars). For statistical significance unpaired student t-test performed at 95% CI and p value<0.05 was considered as significant.